Show HN: Positive News Reader based on sentiment analysis

Re:Show HN: Positive News Reader based on sentiment analysis by Yeroniomus on Saturday April 15, 2017 @05:54PM (#14123058)

Thanks a lot for the link. I've used the technology called Paragraph Vectors https://cs.stanford.edu/~quocle/paragraph_vector.pdf for sentiment features extraction. Training collections were created in a semi-automatic mode and included news title+short description gathered from popular RSS feeds.

[ Parent | on HN ]

Re:Show HN: Positive News Reader based on sentiment analysis by minimaxir on Saturday April 15, 2017 @06:11PM (#14123130)

Sentence vectors encode the data, but how do you determine if a story is positive or negative?

[ Parent | on HN ]

Re:Show HN: Positive News Reader based on sentiment analysis by Yeroniomus on Saturday April 15, 2017 @06:20PM (#14123160)

After collection of possible positive/negative features with weights I used logistic regression classifier with some modifications (e.g. position algorithm) to classify the article. It determines the article polarity based on features (words, phrases and etc.)

[ Parent | on HN ]